Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Vision-Language Reasoning on SelfEval Benchmark (test)
Loading...
55.4
Attribute Binding
CLIP
49.784
51.242
52.7
54.158
Nov 17, 2023
Attribute Binding
Color
Count
Shape
Spatial
Text Corruption
Updated 1mo ago
Evaluation Results
Method
Method
Links
Attribute Binding
Color
Count
Shape
Spatial
Text Corruption
CLIP
Backbone=ViT-L/14, zer...
2023.11
55.4
85.2
67.8
91.1
40.5
51
Random
mode=chance accuracy
2023.11
50
25
25
33
25
20
Feedback
Search any
task
Search any
task
